modelstatus.dev

Claude Opus 4.8

anthropic/claude-opus-4.8

Compare with Claude Opus 4.8 (Fast), Claude Opus 4.7, Claude Opus 4.7 (Fast)

CompareClaude Opus 4.8
  • Amazon Bedrock100%
    Healthy24h 99.96%
    p50
    3.00s
    p99
    8.13s
    Throughput
    64 tps
    Context
    1.0M
    $/Mtok
    $5.00 / $25.00
    amazon-bedrock
  • Anthropic100%
    Healthy24h 99.63%
    p50
    1.98s
    p99
    11.5s
    Throughput
    54 tps
    Context
    1.0M
    $/Mtok
    $5.00 / $25.00
    anthropic
  • Claude Platform on AWS100%
    Healthy24h 99.84%
    p50
    2.41s
    p99
    11.2s
    Throughput
    51 tps
    Context
    1.0M
    $/Mtok
    $5.00 / $25.00
    claude-on-aws
  • Google100%
    Healthy24h 99.97%
    p50
    1.13s
    p99
    5.49s
    Throughput
    63 tps
    Context
    1.0M
    $/Mtok
    $5.00 / $25.00
    google-vertex/global
  • Amazon Bedrock
    No data24h 100%
    p50
    p99
    Throughput
    Context
    1.0M
    $/Mtok
    $5.50 / $27.50
    amazon-bedrock/eu-west-1
  • Amazon Bedrock
    No data24h
    p50
    p99
    Throughput
    Context
    1.0M
    $/Mtok
    $5.50 / $27.50
    amazon-bedrock/us
  • Azure
    No data24h 99.61%
    p50
    2.23s
    p99
    7.17s
    Throughput
    67 tps
    Context
    1.0M
    $/Mtok
    $5.00 / $25.00
    azure/global
  • Azure
    No data24h
    p50
    550ms
    p99
    550ms
    Throughput
    41 tps
    Context
    1.0M
    $/Mtok
    $5.00 / $25.00
    azure/us
  • Google
    No data24h 99.78%
    p50
    p99
    Throughput
    Context
    1.0M
    $/Mtok
    $5.50 / $27.50
    google-vertex/europe
  • Google
    No data24h
    p50
    p99
    Throughput
    Context
    1.0M
    $/Mtok
    $5.50 / $27.50
    google-vertex/us

Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

6 endpoints reporting no data are omitted from the charts.

Availability

Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.

Time to first token

Logarithmic axis — the fleet spans two orders of magnitude. p50 and p99 are OpenRouter's rolling 30-minute windows.

Throughput

Median tokens per second.